© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 21140
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory frameworks related to enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enal
    -0.14
    kın
    -0.14
    .sdk
    -0.12
     Paginator
    -0.12
    vre
    -0.12
    amil
    -0.12
     ÑĩеÑĢ
    -0.12
    vek
    -0.12
    õ
    -0.11
    .mixin
    -0.11
    POSITIVE LOGITS
    -g
    0.55
    _g
    0.40
    -G
    0.39
    ãĤ²
    0.37
    ãĤ¬
    0.36
    "g
    0.35
    ãĤ°
    0.35
    à¤Ĺ
    0.34
     gospel
    0.33
     Gordon
    0.32
    Activations Density 0.690%

    No Known Activations